Two Agents, One Prompt, and Your Weight
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914159693660160 |
|---|---|
| author | Mossel, Elchanan Schreiber, Amnon |
| author_facet | Mossel, Elchanan Schreiber, Amnon |
| contents | We investigate a quantitative variant of the classic Two Doors logic puzzle, in which the answer space is no longer binary, for example when the goal is to recover a numerical fact (such as one's true weight) rather than choose between two doors. The puzzle retains the original structure: one agent always tells the truth, the other always lies. Our central contribution is to identify a class of self-referential prompts that successfully extract the correct quantitative answer under minimal assumptions. We also explore how well does \texttt{ChatGPT} does in reasoning for this problem which is just a little bit out of distribution. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_08232 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Two Agents, One Prompt, and Your Weight Mossel, Elchanan Schreiber, Amnon Logic Probability We investigate a quantitative variant of the classic Two Doors logic puzzle, in which the answer space is no longer binary, for example when the goal is to recover a numerical fact (such as one's true weight) rather than choose between two doors. The puzzle retains the original structure: one agent always tells the truth, the other always lies. Our central contribution is to identify a class of self-referential prompts that successfully extract the correct quantitative answer under minimal assumptions. We also explore how well does \texttt{ChatGPT} does in reasoning for this problem which is just a little bit out of distribution. |
| title | Two Agents, One Prompt, and Your Weight |
| topic | Logic Probability |
| url | https://arxiv.org/abs/2510.08232 |